Dataset Versions

v7

2024-02-07 10:06pm

Generated on Feb 7, 2024

Dataset Split

Train Set 87%
3687Images
Valid Set 8%
330Images
Test Set 5%
200Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Crop: 0% Minimum Zoom, 2% Maximum Zoom
Rotation: Between -15° and +15°
Hue: Between -15° and +15°
Saturation: Between -25% and +25%
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 1.53% of pixels